Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 588 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1204. Min Range: -5.1204

Max Act: 5.1204. Min Act: -0.1700

Data Index: 956106 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 5.1204. Min Range: -5.1204

Max Act: 5.0579. Min Act: -0.1700

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.9954. Min Act: -0.1700

Data Index: 873076 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.9642. Min Act: -0.1700

Data Index: 1198344 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.9017. Min Act: -0.1700

Data Index: 679489 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.9329. Min Act: -0.1700

Data Index: 1297195 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.8704. Min Act: -0.1700

Data Index: 702814 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.8392. Min Act: -0.1700

Data Index: 750473 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.8392. Min Act: -0.1700

Data Index: 1358866 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.8704. Min Act: -0.1700

Data Index: 217544 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7767. Min Act: -0.1700

Data Index: 647065 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7767. Min Act: -0.1700

Data Index: 395662 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7454. Min Act: -0.1700

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7767. Min Act: -0.1700

Data Index: 501968 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7767. Min Act: -0.1700

Data Index: 524959 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7454. Min Act: -0.1700

Data Index: 881578 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7454. Min Act: -0.1700

Data Index: 552750 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7454. Min Act: -0.1700

Data Index: 1166229 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.7767. Min Act: -0.1700

Data Index: 811140 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 5.1204. Min Range: -5.1204

Max Act: 4.6829. Min Act: -0.1700

Data Index: 337615 (C4 (Web Text))

Max Activating Token Index: 568